Voice biometric authentication systems and methods

Abstract

Systems and methods for voice authentication are disclosed. In an embodiment, a computer system may determine that a user is eligible for establishing a voice authentication capability for a user account during a real-time audio communication between a user device corresponding to the user and a communication system associated with an electronic service provider. The computer system may enhance a recording quality of a portion of the real-time audio communication and record a voice sample for the portion of the real-time audio communication at the enhanced recording quality. The computer system may generate a voiceprint based on the voice sample and enable the voice authentication capability such that the user can be authenticated by voice in future audio communications with the communication system in a minimally intrusive fashion where normal conversation can be used to capture voice samples which can be compared to the voiceprint to authenticate the user.

What is claimed is: 
     
       1. A computer system comprising:
 a non-transitory memory storing instructions; and 
 one or more hardware processors configured to execute the instructions and cause the computer system to perform operations comprising:
 based on a real-time audio communication between a user device corresponding to a user and a communication system associated with a service provider, determining that the user is eligible for establishing a voice authentication; 
 initiating a recording of a portion of the real-time audio communication at a first recording quality; 
 enhancing the first recording quality for the portion of the real-time audio communication to a second recording quality that is enhanced with respect to the first recording quality; 
 recording a voice sample for the portion of the real-time audio communication at the second recording quality until the voice sample fulfills a threshold; 
 after the voice sample fulfills the threshold, reverting the recording of the real-time audio communication to the first recording quality; and 
 enabling the voice authentication based on the voice sample. 
 
 
     
     
       2. The computer system of  claim 1 , wherein the operations further comprise:
 causing a notification to be presented in a mobile application corresponding to the user device, wherein the notification includes a prompt for the user to enable the voice authentication; 
 receiving a request to enable the voice authentication; and 
 converting the voice sample into a voiceprint usable in the voice authentication. 
 
     
     
       3. The computer system of  claim 1 , wherein the determining that the user is eligible for establishing the voice authentication comprises determining that the user has initiated a number of real-time audio communications with the communication system that exceeds a threshold number of times. 
     
     
       4. The computer system of  claim 1 , wherein the determining the user is eligible for establishing the voice authentication comprises determining that the user is located within an eligible geofence. 
     
     
       5. The computer system of  claim 1 , wherein the recording the real-time audio communication includes prompting the user provide one or more words for the voice sample when recording the portion of the real-time audio communication at the second recording quality. 
     
     
       6. The computer system of  claim 5 , wherein the operations further comprise:
 storing the recording of the real-time audio communication and metadata associated with the portion of the real-time audio communication, wherein the metadata includes timestamps indicating a location of the portion within the recording of the real-time audio communication. 
 
     
     
       7. The computer system of  claim 1 , wherein the operations further comprise:
 determining that the user does not have a mobile application installed on the user device for enabling the voice authentication; and 
 sending, to a user device associated with the user, a link to a web application configured to allow the user to enable the voice authentication. 
 
     
     
       8. A method comprising:
 recording, by a computer system, an active audio communication between a user device and a server system at a first recording quality; 
 determining that a user account associated with the user device is eligible for establishing voice authentication for future audio communications between the user device and the server system; 
 adjusting, by the computer system, the first recording quality for a portion of the active audio communication to a second recording quality higher than the first recording quality; 
 recording, by the computer system, a voice sample during the portion of the active audio communication at the second recording quality until the voice sample fulfills a threshold; 
 after the voice sample fulfills the threshold, reverting, by the computer system, the recording of the active audio communication to the first recording quality; and 
 prompting, by the computer system, the user device to enable the voice authentication. 
 
     
     
       9. The method of  claim 8 , further comprising converting, by the computer system, the voice sample into a voiceprint for use in the voice authentication in response to receiving an acceptance from the user device to enable the voice authentication. 
     
     
       10. The method of  claim 8 , further comprising:
 identifying, by the computer system, an account corresponding to a phone number for the user device engaged in the active audio communication; and 
 determining, by the computer system, that the account does not have an active mobile application, wherein the prompting the user device to enable the voice authentication comprises sending a prompt to the user device via an email that includes a link to a web application. 
 
     
     
       11. The method of  claim 8 , further comprising:
 receiving, by the computer system, a declination of a prompt to enable the voice authentication; and 
 deleting, by the computer system, the recording of the portion of the audio communication. 
 
     
     
       12. The method of  claim 8 , further comprising
 receiving, by the computer system, a declination to enable the voice authentication; and 
 compressing, by the computer system, the recording including the voice sample. 
 
     
     
       13. The method of  claim 8 , further comprising:
 determining, by the computer system, that the user device is engaged in a second active audio communication after enabling the voice authentication; 
 comparing, by the computer system, a second voice sample of a user of the user device to a voiceprint for the enabled voice authentication; 
 determining, by the computer system, that the second voice sample matches the voiceprint; and 
 authenticating, by the computer system, the user in response to the voice sample matching the voiceprint. 
 
     
     
       14. The method of  claim 13 , further comprising:
 prompting, by the computer system, a user of the user device to speak a set of words for the voice authentication; and 
 collecting, by the computer system, the second voice sample as the user speaks for the voice authentication. 
 
     
     
       15. The method of  claim 8 , wherein the prompting the user device to enable the voice authentication includes sending a request to the user device to complete a one-time password security challenge. 
     
     
       16. A non-transitory machine-readable medium having instructions stored thereon, wherein the instructions are executable to cause a machine of a system to perform operations comprising:
 determining that a user is engaged in a communication being recorded at a first recording quality; 
 recording a voice sample of the user during the communication at a second recording quality that is enhanced in relation to first recording quality; 
 comparing the voice sample of the user to a voiceprint that was generated based on a portion of a recorded previous communication that was recorded at the second recording quality, wherein the portion recorded at the second recording quality was enhanced in relation to a remaining portion of the recorded previous communication; 
 reverting the communication to being recorded at the first recording quality; 
 determining that the voice sample matches the voiceprint; and 
 authenticating the user in response to the voice sample matching the voiceprint. 
 
     
     
       17. The non-transitory machine-readable medium of  claim 16 , wherein the operations further comprise:
 prior to the communication:
 recording the previous communication in which the user is engaged at the first recording quality; 
 determining that the user is eligible for establishing the voiceprint for voice authentication; 
 enhancing the first recording quality to the second recording quality for the portion of the previous communication during the recording the previous communication; 
 prompting the user to enable the voice authentication; and 
 converting the portion of the recorded previous communication into the voiceprint that is usable in the voice authentication based on a user selection to enable the voice authentication. 
 
 
     
     
       18. The non-transitory machine-readable medium of  claim 17 , wherein the prompting the user to enable the voice authentication comprises causing a notification to be presented in a mobile application corresponding to the user, wherein the notification includes a prompt to enable the voice authentication. 
     
     
       19. The non-transitory machine-readable medium of  claim 17 , wherein the operations further comprise:
 receiving a request to disable the voice authentication; and 
 deleting the voiceprint. 
 
     
     
       20. The non-transitory machine-readable medium of  claim 17 , wherein the operations further comprise:
 providing an audio command in the communication to the user to provide a voice sample for the portion of the communication.